检索结果-内蒙古大学图书馆

Novel odor sensing intelligence and surveillance capabilities in controller-responder robots

International Journal of Hybrid Intelligent Systems 2024年第1期20卷 1-22页

作者： Gandhi, Serena Abraham, Ajith Santa Clara High School Santa Clara CA United States School of Computer Science Engineering and Technology Bennett University Greater Noida India

The rise in global travel has led to an increased need for heightened security measures at airports. Despite the best efforts of airport security officers, in the past year, hundreds of kilograms of illegal drugs and thousands of agricultural invasive species have found their way into the country, posing a severe threat to public safety and the environment. Moreover, human threats pose a significant risk to civil aviation, reinforcing the need for advanced security technology. In response to these challenges, NOSI (Novel Odor Sensing Intelligence) and ROSI (Reconnaissance Operations Security Intelligence), intelligence surveillance systems consisting of semi-autonomous controller-responder robots, were developed as a proof of concept to supplement the efforts of security and K-9 (police dogs) operators at airports. NOSI is equipped with multi-channel gas sensors for odor detection, enabling it to identify illegal drugs and invasive species in the baggage handling process, while ROSI is equipped with computer vision to identify individuals already in the government's database of persons of interest. These coordinated robots also provide travelers with important information pertaining to their journey and allow them to trigger emergency alerts. The robots were tested in a custom-designed test bed that replicated both the behind-the-scenes baggage handling and front-office customer service operations of an airport, thus simulating a realistic airport-like setting. Based on design criteria, NOSI and ROSI demonstrated success rates of 73.4 percent and 69.8 percent, respectively. Improvements in areas of robot stability, sensor accuracy, and feature expansion were documented for further development. In conclusion, the NOSI and ROSI framework can enhance the efficiency and accuracy of airport infrastructure monitoring and supplement the capabilities of human and K9 operators. Overall, this approach can potentially revolutionize operations in various infrastructures and rep

关键词： airport security drug human-robot collaboration Intelligence surveillance systems invasive species detection semi-autonomous controller-responder robots

来源：评论

学校读者我要写书评

暂无评论

Multi-Query Vehicle Re-Identification: Viewpoint-Conditioned Network, Unified Dataset and New Metric

引用

IEEE Transactions on Image Processing 2023年 32卷 5948-5960页

作者： Zheng, Aihua Zhang, Chaobin Li, Chenglong Tang, Jin Tan, Chang Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Hefei230601 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Iflytek Company Ltd. Hefei230088 China

Existing vehicle re-identification methods mainly rely on the single query, which has limited information for vehicle representation and thus significantly hinders the performance of vehicle Re-ID in complicated surveillance networks. In this paper, we propose a more realistic and easily accessible task, called multi-query vehicle Re-ID, which leverages multiple queries to overcome viewpoint limitation of single one. Based on this task, we make three major contributions. First, we design a novel viewpoint-conditioned network (VCNet), which adaptively combines the complementary information from different vehicle viewpoints, for multi-query vehicle Re-ID. Moreover, to deal with the problem of missing vehicle viewpoints, we propose a cross-view feature recovery module which recovers the features of the missing viewpoints by learnt the correlation between the features of available and missing viewpoints. Second, we create a unified benchmark dataset, taken by 6142 cameras from a real-life transportation surveillance system, with comprehensive viewpoints and large number of crossed scenes of each vehicle for multi-query vehicle Re-ID evaluation. Finally, we design a new evaluation metric, called mean cross-scene precision (mCSP), which measures the ability of cross-scene recognition by suppressing the positive samples with similar viewpoints from the same camera. Comprehensive experiments validate the superiority of the proposed method against other methods, as well as the effectiveness of the designed metric in the evaluation of multi-query vehicle Re-ID. The codes and dataset are available at: https://***/zhangchaobin001/VCNet © 1992-2012 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Enhancing Weakly Supervised Medical Segmentation via Heterogeneous Co-training with Box-Wise Augmentation and Pseudo-Label Filtering 6th

Enhancing Weakly Supervised Medical Segmentation via Hetero...

引用

6th IFIP TC 12 International Conference on Intelligence science, ICIS 2024

作者： Wang, You Qi, Lei Yu, Qian Shi, Yinghuan Gao, Yang State Key Laboratory of Novel Software Technology National Insititute of Health-care Data Science Nanjing University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China School of Data and Computer Science Shandong Woman’s University Jinan China

ISBN: (纸本)9783031712524

In this paper, we introduce an innovative approach to weakly supervised medical image segmentation with box annotations. Different from the previous methods which simply utilize a single conventional network with the same augmentation techniques widely used in supervised segmentation, we aim to introduce diverse augmentations and heterogenous networks to leverage the box annotations for promising generalization ability. Specifically, to amplify the diversity between the contents within the box and its surroundings, we propose the interior and exterior box augmentation (IEBA) technique, in which distinct augmentation techniques are employed for regions inside and outside the bounding boxes. Also, for the purpose of selecting pseudo-labels of superior quality, we propose the pseudo-label filter module (PLFM) to eliminate unreliable pseudo-labels. Besides, as CNN demonstrates superior capabilities in acquiring local information, and ViT specializes in capturing global context, we facilitate a bidirectional learning process between CNN and ViT through quadruple cross consistency losses (QCCL). In inference, we only employ the superior model from the validation set to obtain parameter efficiency. Our approach is evaluated across four tasks on two public datasets, utilizing the 3D dice similarity coefficient as the evaluation metric. The experimental results show that the proposed method outperforms the state-of-the-art comparison methods. © IFIP International Federation for Information Processing 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Lane detection networks based on deep neural networks and temporal information

引用

Alexandria engineering Journal 2024年 98卷 10-18页

作者： Lin, Huei-Yung Chang, Chun-Ke Tran, Van Luan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei106 Taiwan Department of Electrical Engineering National Chung Cheng University Chiayi621 Taiwan School of Engineering Eastern International University Binh Duong Viet Nam

In the past few years, the lane detection technique has become a key factor for autonomous driving systems and self-driving cars on the road. Among the various vehicle subsystems, the lane detection module is one of the essential parts of the Advanced Driver Assistance System (ADAS). Conventional lane detection approaches use machine vision algorithms to find straight lines in road scene images. However, it is challenging to identify straight or curved lane markings in complex environments. To deal with this problem, this paper presents a lane detection technique based on deep learning. It is combined with a 3D convolutional network, so the temporal information is added to the network architecture. Using the front camera images, the system can immediately detect the lane marking information ahead. Moreover, we propose an approach for improvement by adding the time axis to the network architecture. In addition to using 3D-ResNet50, the temporal convolution and spatial convolution are separated for processing. The accuracy is 91.34% improved after adding time and space split convolution with LeakyReLU. The experiments carried out using real scene images have demonstrated the feasibility of the proposed technique for applications to various complex scenes. © 2024 The Author(s)

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Research on Spatio-Temporal Data Processing Framework 21

Research on Spatio-Temporal Data Processing Framework

引用

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： He, Liu Ao, Ren Jianping, Li College of Computer Science Chongqing University Chongqing401331 China Chongqing Academy of Educational Sciences Chongqing400015 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798331519254

Aiming at the challenges in time series data processing, this paper proposes a new deep learning model, which uses Spiking neurons with time series processing ability to organize, represent and transmit information instead of traditional methods. By combining the time representation characteristics of Spiking neurons with the hierarchical deep connection advantages of complex networks, this study explores a deep learning model combining time and space, which shows significant advantages in the representation and processing ability of time series data. Specifically, we design and implement a model that combines the Spiking mechanism with complex networks. This model can effectively capture the dynamic changes in time series data and improve processing efficiency. The experimental results show that the proposed model has achieved good performance on multiple time series data sets, which verifies its effectiveness and feasibility in time series data representation and processing. This study provides a new method for the field of time series data analysis, which is expected to be widely used in intelligent systems, financial forecasting, bioinformatics and other fields. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Real-Time Edge Computing Services for Internet of Things-based Cloud Networks 15

Real-Time Edge Computing Services for Internet of Things-bas...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Kashyap, Sneha Seth, Jyoti Hannah Jessie Rani, R. Arka Jain University Department of Computer Science & It Jharkhand Jamshedpur India Vivekananda Global University Department of Computer Science & Engineering Jaipur India School of Engineering and Technology Department of Electrical and Electronics Engineering Karnataka Bangalore India

ISBN: (纸本)9798350370249

the emergence of the Internet of Things (IoT) gadgets and cloud-enabled networks has brought about a dramatic growth in the quantity and kinds of programs that require real-time facet computing offerings. Aspect computing is a rising location of allotted computing that methods facts toward the cease person or tool, supplying low-latency responses to operations and analytics. It enables quicker and more dependable facts-extensive applications that can be personalized to consumer alternatives and needs. This paper discusses the design and implementation of real-time edge computing offerings for IoT-primarily based cloud networks, focusing on key components of the device structure, including carrier deployment, aid management, protection, and scalability. Furthermore, the paper describes the usage of area computing for IoT programs, which include video surveillance, domestic automation, and smart town solutions. Subsequently, the paper presents a survey of cutting-edge area computing companies, summarizing their offerings, business models, and services. © 2024 IEEE.

关键词： Analytics Applications Automation Business Models Computing Real-Time Services

来源：评论

学校读者我要写书评

暂无评论

Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection 24

Dual-Modeling Decouple Distillation for Unsupervised Anomaly...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Xinyue Wang, Jianyuan Leng, Biao Zhang, Shuo School of Computer Science and Engineering Beihang University Beijing China Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education School of Intelligence Science and Technology University of Science and Technology Beijing Beijing China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer & Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798400706868

Knowledge distillation based on student-teacher network is one of the mainstream solution paradigms for the challenging unsupervised Anomaly Detection task, utilizing the difference in representation capabilities of the teacher and student networks to implement anomaly localization. However, over-generalization of the student network to the teacher network may lead to negligible differences in representation capabilities of anomaly, thus affecting the detection effectiveness. Existing methods address the possible over-generalization by using differentiated students and teachers from the structural perspective or explicitly expanding distilled information from the content perspective, which inevitably results in an increased likelihood of underfitting of the student network and poor anomaly detection capabilities in anomaly center or edge. In this paper, we propose Dual-Modeling Decouple Distillation (DMDD) for the unsupervised Anomaly Detection. In DMDD, a Decouple Student-Teacher Network is proposed to decouple the initial student features into normality and abnormality features. We further introduce Dual-Modeling Distillation based on normal-anomalous image pairs, fitting normality features of anomalous image and the teacher features of the corresponding normal image, widening the distance between abnormality features and the teacher features in anomalous regions. Synthesizing these two distillation ideas, we achieve anomaly detection which focuses on both edge and center of anomaly. Finally, a Multi-perception Segmentation Network is proposed to achieve focused anomaly map fusion based on multiple attention. Experimental results on MVTec AD show that DMDD surpasses SOTA localization performance of previous knowledge distillation-based methods, reaching 98.85% on pixel-level AUC and 96.13% on PRO. © 2024 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Smart City Survey on AIoT Using Machine Learning, Deep Learning, and Its Computing Tools 5th

Smart City Survey on AIoT Using Machine Learning, Deep Lear...

引用

5th International Conference on Advances in Distributed Computing and Machine Learning, ICADCML 2024

作者： Priakanth, P. Jothimani, K. Gopikrishnan, S. Linga Reddy, C. Department of Computer Science and Design Kongu Engineering College Erode India School of Computer Science and Engineering VIT-AP University Amaravati India Department of Information and Communication Technology University of Agder Kristiansand Norway

ISBN: (纸本)9789819735228

Urban-city administrators are proceeding on smart applications with the fully integrated IoT-artificial intelligence analytics explication assists intelligent-safer workstation, immediate happenstance response, disaster control management including smart electricity, trash, air and water allowing them to produce more prominent levels of flexibility, yielding, sustainability and profitability. Though smart city notion is gradually developing and yet not established all over the world owing to economical, technological, and administrating blockades. This perspective paper aims to accomplish a review of IoT-enabled artificial intelligence regarding the usage of machine learning and deep learning for the development of smarter cities in addition to different computing tools to employ methods, platforms, architectures, and its real-world enactment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

MaGIC: Multi-modality Guided Image Completion 12

MaGIC: Multi-modality Guided Image Completion

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Hao Yu, Yongsheng Luo, Tiejian Fan, Heng Zhang, Libo School of Computer Science and Technology University of Chinese Academy of Sciences China Institute of Software Chinese Academy of Sciences China Department of Computer Science University of Rochester United States Department of Computer Science and Engineering University of North Texas United States

Vanilla image completion approaches exhibit sensitivity to large missing regions, attributed to the limited availability of reference information for plausible generation. To mitigate this, existing methods incorporate the extra cue as a guidance for image completion. Despite improvements, these approaches are often restricted to employing a single modality (e.g., segmentation or sketch maps), which lacks scalability in leveraging multi-modality for more plausible completion. In this paper, we propose a novel, simple yet effective method for Multi-modal Guided Image Completion, dubbed MaGIC, which not only supports a wide range of single modality as the guidance (e.g., text, canny edge, sketch, segmentation, depth, and pose), but also adapts to arbitrarily customized combination of these modalities (i.e., arbitrary multi-modality) for image completion. For building MaGIC, we first introduce a modality-specific conditional U-Net (MCU-Net) that injects single-modal signals into a U-Net denoiser for single-modal guided image completion. Then, we devise a consistent modality blending (CMB) method to leverage modality signals encoded in multiple learned MCU-Nets through gradient guidance in latent space. Our CMB is training-free, thereby avoiding the cumbersome joint re-training of different modalities, which is the secret of MaGIC to achieve exceptional flexibility in accommodating new modalities for completion. Experiments show the superiority of MaGIC over state-of-the-art methods and its generalization to various completion tasks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Multiple HAPS-Based Hybrid FSO/RF Space-Air-Ground Network 16

Performance Analysis of Multiple HAPS-Based Hybrid FSO/RF Sp...

引用

16th International Conference on COMmunication Systems and NETworkS, COMSNETS 2024

作者： Singh, Deepshikha Swaminathan, R. Marrapu, Aravind Madhukumar, A.S. Indian Institute of Technology Indore Department of Electrical Engineering India School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350383119

Sixth generation (6G) networks are anticipated to support increasingly data-hungry applications by expanding the network capabilities and connectivity. Free space optics (FSO) communication with space-air-ground (SAG) network becomes a potential solution to meet the enormous traffic demands and ubiquitous connectivity requirement in 6G networks. In spite of various advantages offered by FSO communication such as high bandwidth availability, large unlicensed spectrum, better security, etc., the FSO link exhibits a high degree of responsiveness to atmospheric turbulence, attenuation, and pointing errors. Thus to mitigate the severe atmospheric effects, we propose a multiple high-altitude platform station (HAPS)-based SAG network, where HAPS functions as a decode-and-forward (DF) relay node between ground station and satellite. We take into account a hybrid FSO/radio frequency (RF) link for connecting ground station and HAPS nodes and an FSO link between HAPS and satellite. The performance analysis of the proposed SAG network involves evaluating the outage probability and average symbol error rate (SER) considering the presence of pointing errors and assuming Málaga distribution in case of FSO and shadowed k - μ fading distribution in case of RF link. Furthermore, asymptotic analysis is conducted to determine the diversity gain of the proposed system. Numerical results demonstrate that the proposed multiple HAPS-based hybrid FSO/RF SAG network outperforms all other existing HAPS-based SAG network models in the literature. © 2024 IEEE.

关键词： DF relaying free space optics (FSO) high-altitude platform station (HAPS) hybrid FSO/RF performance analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：